{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T15:58:13Z","timestamp":1765209493284,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,17]],"date-time":"2023-11-17T00:00:00Z","timestamp":1700179200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,17]]},"DOI":"10.1145\/3652628.3652655","type":"proceedings-article","created":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T10:36:46Z","timestamp":1716460606000},"page":"155-160","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Flexible Mobility MADDPG Algorithm for UAV Swarm Unknown Region Searching"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7947-6842","authenticated-orcid":false,"given":"Heng","family":"Huang","sequence":"first","affiliation":[{"name":"Shenzhen Ecological Environment Monitoring Center Station, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5629-7907","authenticated-orcid":false,"given":"Jianfeng","family":"Guo","sequence":"additional","affiliation":[{"name":"Shenzhen Ecological Environment Monitoring Center Station, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6773-8607","authenticated-orcid":false,"given":"Kun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Beijing Safety Test Technology Co., Ltd, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0650-2708","authenticated-orcid":false,"given":"Biqi","family":"Peng","sequence":"additional","affiliation":[{"name":"Beijing Safety Test Technology Co., Ltd, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,23]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jii.2019.100106"},{"key":"e_1_3_2_1_2_1","volume-title":"Human-level control through deep reinforcement learning. nature","author":"Volodymyr","year":"2015","unstructured":"MNIH, Volodymyr, Human-level control through deep reinforcement learning. nature, 2015, 518.7540: 529-533."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"e_1_3_2_1_4_1","first-page":"34","article-title":"Deep reinforcement learning: A brief survey","author":"Kai","year":"2017","unstructured":"ARULKUMARAN, Kai, Deep reinforcement learning: A brief survey. IEEE Signal Processing Magazine, 2017, 34.6: 26-38.","journal-title":"IEEE Signal Processing Magazine"},{"key":"e_1_3_2_1_5_1","volume-title":"Deep reinforcement learning for multiagent systems: A review of challenges, solutions, and applications","author":"Thanh Thi NGUYEN","year":"2020","unstructured":"NGUYEN, Thanh Thi; NGUYEN, Ngoc Duy; NAHAVANDI, Saeid. Deep reinforcement learning for multiagent systems: A review of challenges, solutions, and applications. IEEE transactions on cybernetics, 2020, 50.9: 3826-3839."},{"key":"e_1_3_2_1_6_1","volume-title":"On-line Q-learning Using Connectionist Systems","author":"Rummery GA","year":"1994","unstructured":"Rummery GA, Niranjan M. On-line Q-learning Using Connectionist Systems. Cambridge: University of Cambridge, 1994."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_8_1","first-page":"1889","volume-title":"International conference on machine learning. PMLR","author":"John","year":"2015","unstructured":"SCHULMAN, John, Trust region policy optimization. In: International conference on machine learning. PMLR, 2015. p. 1889-1897."},{"key":"e_1_3_2_1_9_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"John","year":"2017","unstructured":"SCHULMAN, John, Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347, 2017."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"e_1_3_2_1_11_1","volume-title":"4th International Conference on Learning Representations","author":"Lillicrap TP","year":"2016","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Continuous control with deep reinforcement learning. 4th International Conference on Learning Representations. San Juan, UT, USA. 2016."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Haarnoja T","year":"2018","unstructured":"Haarnoja T, Zhou A, Abbeel P, Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. Proceedings of the 35th International Conference on Machine Learning. Long Beach, CA, USA. 2018. 1861\u20131870."},{"key":"e_1_3_2_1_13_1","first-page":"1928","volume-title":"International conference on machine learning. PMLR","author":"Volodymyr","year":"2016","unstructured":"MNIH, Volodymyr, Asynchronous methods for deep reinforcement learning. In: International conference on machine learning. PMLR, 2016. p. 1928-1937."},{"key":"e_1_3_2_1_14_1","volume-title":"Multi-agent actor-critic for mixed cooperative-competitive environments. Advances in neural information processing systems","author":"Ryan","year":"2017","unstructured":"LOWE, Ryan, Multi-agent actor-critic for mixed cooperative-competitive environments. Advances in neural information processing systems, 2017, 30."},{"key":"e_1_3_2_1_15_1","volume-title":"Advances in Production Management Systems. Artificial Intelligence for Sustainable and Resilient Production Systems: IFIP WG 5.7 International Conference","author":"Oliver P\u00dcTZ","year":"2021","unstructured":"LOHSE, Oliver; P\u00dcTZ, Noah; H\u00d6RMANN, Korbinian. Implementing an online scheduling approach for production with multi agent proximal policy optimization (MAPPO). In: Advances in Production Management Systems. Artificial Intelligence for Sustainable and Resilient Production Systems: IFIP WG 5.7 International Conference, APMS, 2021. p. 586-595."},{"key":"e_1_3_2_1_16_1","volume-title":"Express uav swarm path planning with vnd enhanced memetic algorithm. In:\u00a0Proceedings of the 2018 International Conference on Computing and Data Engineering","author":"Fanli LI","year":"2018","unstructured":"DUAN, Fanli; LI, Xiaohui; ZHAO, Yi. Express uav swarm path planning with vnd enhanced memetic algorithm. In:\u00a0Proceedings of the 2018 International Conference on Computing and Data Engineering. 2018. p. 93-97."},{"key":"e_1_3_2_1_17_1","first-page":"43","article-title":"Cooperative pursuit strategy for multi-UAVs based on DE-MADDPG algorithm","author":"Zh","year":"2022","unstructured":"FU, X.; WANG, H.; XU, Zh. Cooperative pursuit strategy for multi-UAVs based on DE-MADDPG algorithm. Acta Aeronautica et Astronautica Sinica, 2022, 43.5: 325311-325311.","journal-title":"Acta Aeronautica et Astronautica Sinica"},{"key":"e_1_3_2_1_18_1","first-page":"103","volume-title":"2017 10th International Conference on Intelligent Computation Technology and Automation (ICICTA). IEEE","author":"Fang XIAOFENG","year":"2017","unstructured":"BIN, Fang; XIAOFENG, Feng; SHUO, Xu. Research on cooperative collision avoidance problem of multiple UAV based on reinforcement learning. In: 2017 10th International Conference on Intelligent Computation Technology and Automation (ICICTA). IEEE, 2017. p. 103-109."},{"key":"e_1_3_2_1_19_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Ashish","year":"2017","unstructured":"VASWANI, Ashish, Attention is all you need. Advances in neural information processing systems, 2017, 30."}],"event":{"name":"ICAICE 2023: The 4th International Conference on Artificial Intelligence and Computer Engineering","acronym":"ICAICE 2023","location":"Dalian China"},"container-title":["Proceedings of the 4th International Conference on Artificial Intelligence and Computer Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652628.3652655","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652628.3652655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T15:28:57Z","timestamp":1765207737000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652628.3652655"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,17]]},"references-count":19,"alternative-id":["10.1145\/3652628.3652655","10.1145\/3652628"],"URL":"https:\/\/doi.org\/10.1145\/3652628.3652655","relation":{},"subject":[],"published":{"date-parts":[[2023,11,17]]},"assertion":[{"value":"2024-05-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}